With more than 320,000 deaths across the globe due to COVID-19, doctors have struggled to identify why some people get fatally ill, while others have light to no symptoms of the novel coronavirus. Now, thanks to a new study, doctors may be able to predict a patient's risk of death due to COVID-19 up to ten days before.
According to the study published last week in the journal Nature Machine Intelligence, researchers created a model that examines three biological markers found in coronavirus patients' blood that could indicate whether a patient could become seriously ill more than ten days ahead of time, with 90% accuracy.
Researchers hailed the new clues as a crucial way to distinguish "the vast majority of cases that require immediate medical attention." The study's authors wrote that their model is able to provide a "simple and intuitive clinical test to precisely and quickly quantify the risk of death."
Doctors have known for awhile now that people with underlying health conditions are at greater risk of contracting a fatal version of COVID-19, however, using the biological markers can give medical personnel a heads up on which patients would require more drastic treatment.
In order to identify the common biological markers that indicate the higher risk of dying from the coronavirus, researchers analyzed blood samples taken repeatedly from 485 coronavirus patients at Tongi Hospital in Wuhan, China, between Jan. 10 and Feb. 18. Researchers tested the blood samples for a variety of kidney, heart and other blood-clotting issues, noting whether those patients survived or died. The researchers then used a machine-learning algorithm to look for patterns in the biological markers.
According to the study, researchers found that:
1) High levels of an enzyme called lactic dehydrogenase (LDH), which is associated with lung damage and tissue breakdown seen in pneumonia cases.
2) Low levels of lymphocytes - the white blood cells that work to keep the body clear of invading pathogens like the coronavirus.
3) An increase in high-sensitivity C-reactive proteins. Those can indicate inflammation in the lungs.
If a patient presents with all three markers, researchers say their computer model can predict how likely those hospital patients will die from COVID-19 up to ten days in advance.
"The three key features, LDH, lymphocytes and hs-CRP, can be easily collected in any hospital," the researchers wrote in the study. "In crowded hospitals, and with shortages of medical resources, this simple model can help to quickly prioritize patients, especially during a pandemic when limited healthcare resources have to be allocated."
A second study published in the Journal of the American Medical Association on Tuesday, appears to back up the researchers' findings. The study published in the AMA Journal looked at ten biomarkers that could help doctors asses patients' risk levels of becoming critically ill, or dying from COVID-19.
Two of the biomarkers overlapped with the second study, including high levels of LDH and the high neutrophil to lymphoctye ratio (which is associated with lower levels of lymphocytes).
Other risk factors included a history of cancer, high number of preexisting conditions, older age, shortness of breath, coughing up blood, unconsciousness, abnormal chest X-rays, and high levels of bulirubin - which can indicate liver damage.
Using those biomarkers, researchers created an online "coronavirus risk calculator" that could help predict which patients will become critically ill from COVID-19.
"If the patient's estimated risk for critical illness is low, the clinician may choose to monitor, whereas high-risk estimates might support aggressive treatment or admission to the ICU," they said.
Photos: Getty Images